Elektrine lite

← Feed

@RustyNova@lemmy.world

2026-11-08 18:38 UTC

Good analysis, unfortunately it is false. We are literally 9 people, and our workload is maxed. We are trying to recruit but it’s a really specific line of development so it’s rare there’s anyone (and when they do they may be more interested in bigger enterprises) The pressure comes from bad docs slowing humans, but not AI, our software provider asking us to use AI before doing tickets, I am the only one that is anti ai, and despite my complaining they continued "Ok here’s this script to be made, you have 5 days before the client migration we need it ready, tested, and prepared to go live, just use Claude to do it as it’s faster". I did use Claude for that one, not because I wanted to, I’d love to write that on my own, but the deadline is impossible for even a experienced developer in that specific field. I have come to terms with the AI usage, and I won’t change job as AI is the only bad part in it, and I might change to a company being even more into slop… I am just looking to see how I could fight it and whether making anthropic loose even more money is worth the environmental concerns

Replies (1)

  • @kunaltyagi@programming.dev 2026-11-08 22:21

    Use the AI to fix technical debt. A lot of the changes needed to make codebase good were just humanly not possible (given the priority and urgency), but now you have a stochastic parrot to do the grunt work. Setup CI, align docs to actual code, improve interfaces, refactor for the long term and not just what the next ticket needed. Treat it like free labour for some easy but time consuming stuff aka intern. Using it per ticket without removing old debt will incur more debt. Once you are happy enough with the codebase that giving a ticket to a really capable but still stupid intern isn’t gonna result in unmanageable shit, then you can start tackling tickets with LLM harness like: adding a MCVE or checking if a ticket has enough info. Outright solving tickets with AI will result in the team getting increasingly unfamiliar with their own codebase making. That will have similar effect has hiring a new senior engineer to any project with no team and only interns (LLM): lots of ideas and capabilities but almost all of the time is spent in understanding the effing codebase. Using random ass scripts to make certain ticket managers happy will ‘help now’, but it’ll be really bad for a team of 10. Increasing velocity needs a large magnitude (ticket size * ticket count) as well as the right direction (based on codebase) so the mgmt strategy is bonkers.

    Open ##5548496